INDEX

Explanations

references to objectives and intentions in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ьаж

-0.98

afficheront

-0.89

httphttps

-0.89

%");

-0.87

orianCalendar

-0.83

 NSCoder

-0.83

 GenerationType

-0.83

 MenuView

-0.83

]--;

-0.82

Дереккөздер

-0.82

POSITIVE LOGITS

 purpose

2.13

 Purpose

2.11

Purpose

2.03

 purposes

1.97

 PURPOSE

1.90

purpose

1.88

PURPOSE

1.84

 Purposes

1.69

purposes

1.32

 propósitos

1.22

Activations Density 0.057%

references to objectives and intentions in the text

No Comments

No Known Activations